Semantic segmentation method for myocardial contrast echocardiogram based on DeepLabV3+ deep learning architecture

Myocardial contrast echocardiography (MCE) has been proposed as a method to assess myocardial perfusion for the detection of coronary artery diseases in a non-invasive way. As a critical step of automatic MCE perfusion quantification, myocardium segmentation from the MCE frames faces many challenges due to the low image quality and complex myocardial structure. In this paper, a deep learning semantic segmentation method is proposed based on a modified DeepLabV3+ structure with an atrous convolution and atrous spatial pyramid pooling module. The model was trained separately on three chamber views (apical two-chamber view, apical three-chamber view, and apical four-chamber view) on 100 patients' MCE sequences, divided by a proportion of 7:3 into training and testing datasets. The results evaluated by using the dice coefficient (0.84, 0.84, and 0.86 for three chamber views respectively) and Intersection over Union(0.74, 0.72 and 0.75 for three chamber views respectively) demonstrated the better performance of the proposed method compared to other state-of-the-art methods, including the original DeepLabV3+, PSPnet, and U-net. In addition, we conducted a trade-off comparison between model performance and complexity in different depths of the backbone convolution network, which illustrated model application feasibility.